Data+ 2017 Wraps Up 3rd Year

Data+ 2017 students pose for a group photo

This summer, 70 undergraduates and 27 graduate student mentors participated in a broad spectrum of interdisciplinary data projects as part of the Data+ Summer Program at Duke, which is run by the Information Initiative @Duke in partnership with SSRIMedX, and other Duke departments, Initiatives, and industry sponsors (see full list below).

Students and mentors were divided up into 25 different project teams learning to marshal, analyze, and visualize data challenges provided by a wide range of faculty and corporate sponsors, including several Duke Health sectors, the City of Durham, TD Bank, and many more.

Each project provides students the experience of working with real-world problems and questions, and to use real data to formulate solutions and visualizations from the data. On occasion, the work Data+ students begin over the summer continues after the program is over in the form of published papers, app development, the creation of new datasets that will be used by the project client, or in the development of grant proposals.

There were also two workshops this summer for Data+ students involved in Durham and Duke Health Themed projects. Students working in teams related to Duke Health or City of Durham projects presented their work to clients and other stakeholders to discuss the data and ways it could be used moving forward. "It was exciting to present for and discuss with such an audience, which was delightfully engaged and creative in new takes on our project,” said Willem van den Boom, mentor for the Controlled Substance Monitoring and Visualization team.

After 10 weeks, students wrap up the program with a poster session to highlight their process and results. The 2017 Data+ Poster Session was held on July 28, 2017 in the Gross Hall Energy Hub Atrium. With over 250 attendees from the university and from outside partners, students were able to widely share their results many interested parties.

Data+ students Esko Brummel and Jon 
Benhardt describe their work on Duke Research 
based on Large-Scale Faculty Publications

Susie Choi and Ellie Wood share their work on 
Visualizing Real Time Data from Mobile Health









Currently in its third year, Data+ continues to grow and to provide well rounded, challenging interdisciplinary data experiences for students and faculty alike. Faculty clients, student mentors, and students all report that Data+ has enhanced their abilities to marshal, analyze, and visualize data, and that Data+ provides a unique educational and research experience that is highly desirable:

"The project mentor was fantastic. The three students I worked with were superb. We were able to make great progress that will lead to journal publications and grant proposals." - Wilkins Aquino, Electrical & Computer Engineering Faculty Client, Classification of Vascular Anomalies using Continuous Doppler Ultrasound and Machine Learning

“The Data+ team created two new datasets that we'll immediately deploy as a part of our core research efforts and will serve as the basis for an upcoming Bass Connections in Energy project. The outputs will be used towards two new research projects on energy infrastructure and access in developing countries, and will serve as the ground truth data for developing machine learning techniques for identifying energy infrastructure and access. The students were fantastic - hardworking, passionate about their work, and all-around wonderful people to work with.” - Kyle Bradbury, Managing Director, Duke Energy Data Analytics Lab, Electricity Access in Developing Countries from Aerial Imagery

Students gained valuable experience both for their future research and for their future careers, as well as a new appreciation for data and the many ways it can be applied to the world around us.

Data+ gave me a broader perspective of what Data Science research is. At first I thought Data Science was only the statistical analysis of data, but now I know that it involves much more than that, such as visualization, interpretation, and data management. I gained a deeper understanding of how to use R and ggplot2, as well as a better understanding of what Data Science is and how it's applied.” - Devri Adams, Environmental Science, Data Viz for Long-term Ecological Research and Curricula

"My participation in the Data+ program has shown me how to successfully work with a dynamic team. Each of my team members were fundamentally different in course interests and background, yet we came together to create a polished product in which we each were a point person for a specific portion. I have also gained confidence in my ability to learn new skills, as I basically taught myself (through Google and asking teammates) how to program in R over this summer." - Serge Assad, Biomedical Engineering, Electrical & Computer Engineering, Classification of Vascular Anomalies using Continuous Doppler Ultrasound and Machine Learning

“Data+ taught me just how much elbow grease goes into Data Science research: from the study coordinators collecting data, to the coders cleaning the data, to the statisticians analyzing the data, and the UI/UX pros presenting the data. Before Data+, data science research sounded like a non-collaborative job involving PhD-level statistical concepts. Data+, however, showed me that there is a place for collaborative workers from all different backgrounds (and of all skill levels) in Data Science research. Participating in Data+ has enriched my technical skills as a coder; I am now able to navigate soft wares and employ coding languages that I was not at all familiar with before the start of the program. Even more valuable, however, are the "soft" skills I have gained -- specifically, the ability to approach collaboration with an open mind.”- Susie Choi, Computer Science, Visualizing Real Time Data from Mobile Health Technologies

Sometimes, the work students and mentors do with their project teams also leads to employment opportunities from their experience with Data+:

“I gained valuable program management experience. Given that after the program was over, I got hired as a consultant manager at CollegeVine, I'd say it paid off.” Stephan Waldschmidt, English, Quantified Feminism and the Bechdel Test

Data+ is sponsored by Bass Connections, the Information Initiative at Duke, the Social Science Research Institute, the departments of Mathematics and Statistical Science and MEDx.

Other Duke sponsors include DTECH, Duke Health, Sanford School of Public Policy, Nicholas School of the Environment, Development and Alumni Affairs, Energy Initiative, Franklin Humanities Institute, Duke Institute for Brain Sciences, Office for Information Technology and the Office of the Provost, as well as the departments of Electrical & Computer Engineering, Computer Science, Biomedical Engineering, Biostatistics & Bioinformatics and Biology.
Government funding comes from the National Science Foundation.

Outside funding comes from Accenture, Academic Analytics, Counter Tools and an anonymous donation.

Community partnerships, data and interesting problems come from the Durham Police Department, Durham Neighborhood Compass, Cary Institute of Ecosystem Studies, Duke Marine Lab, Center for Child and Family Policy, Northeast Ohio Medical University, TD Bank, Epsilon, Duke School of Nursing, University of Southern California, Durham Bicycle and Pedestrian Advisory Commission, Duke Surgery, MyHealth Teams, North Carolina Museum of Art and Scholars@Duke.

To participate: Proposals for Data+ Summer 2018 are currently being accepted until November 17, 2017. Interested faculty should review the proposal guide and contact Paul Bendich for more information.

Interested industry partners can get more information here.

Student applications will open in December, so keep an eye out for our announcement and for the 2018 Data+ project fair this Winter!



Ariel Dawn